Adaptive canonical correlation analysis for harmonic stimulation frequencies recognition in SSVEP-based BCIs

Abstract

Steady-state visual evoked potential (SSVEP) is the brain’s response to quickly repetitive visual stimuluswith a certain frequency. To increase the information transfer rate (ITR) in SSVEP-based systems, due to the frequencyresolution restriction, we are forced to broaden the frequency range, which causes harmonic frequencies to come intothe stimulation frequency range. Conventional canonical correlation analysis (CCA) may be associated with error forSSVEP frequency recognition at stimulation frequencies with harmonic relations. The number of harmonics consideredto construct reference signals are determined adaptively; for frequencies whose second harmonic exists in the frequencyrange, two harmonics are used, and for other frequencies, just one harmonic is used. After constructing reference signalsand recognizing the frequency corresponding to the maximum value of correlation by CCA, the target frequency isdetermined after a postprocessing step. Results show that for the 8-s time window length, the average classificationaccuracy for the adaptive CCA was 84%, while the corresponding values for the CCA with one harmonic (N = 1) andtwo harmonics (N = 2) were 78% and 74%, respectively. For 4-s length, this accuracy for the adaptive CCA was 86%,while it was 78% for both harmonic selection modes of the standard CCA, N = 1 and N = 2. In SSVEP applicationswith harmonic stimulation frequencies, the adaptive CCA has significantly improved the frequency recognition accuracyin comparison with the popularly standard CCA method. The proposed method can be useful for SSVEP-based BCIsystems that use broad ranges of stimulation frequencies with harmonic relation.